© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48485
    Prev
    Next
    INDEX
    Explanations

    surface or interface boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {name
    -0.08
    æ¡ijæĭ¿
    -0.08
     kesin
    -0.07
    åĢ¶
    -0.07
    èĩªæŁ¥
    -0.07
    AGR
    -0.07
    è¶ħåīį
    -0.07
    åd
    -0.07
    uvre
    -0.07
     outright
    -0.07
    POSITIVE LOGITS
     surface
    0.12
    surface
    0.11
    表éĿ¢
    0.10
    urface
    0.09
     Surface
    0.09
    表éĿ¢çļĦ
    0.09
     повеÑĢÑħноÑģÑĤÑĮ
    0.09
     surfaces
    0.09
     onto
    0.08
     повеÑĢÑħноÑģÑĤи
    0.08
    Activations Density 0.066%

    No Known Activations